Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Marta Marchiori Manerba"'
Publikováno v:
ECML PKDD 2022-Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 483–497, Grenoble, France, 19-23/09/2022
Communications in Computer and Information Science ISBN: 9783031236174
Communications in Computer and Information Science ISBN: 9783031236174
Biases can arise and be introduced during each phase of a supervised learning pipeline, eventually leading to harm. Within the task of automatic abusive language detection, this matter becomes particularly severe since unintended bias towards sensiti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::833d9fd0fcd70b2abcea59d294237317
https://openportal.isti.cnr.it/doc?id=people______::fa577cc03550d472fe22c71ada549a45
https://openportal.isti.cnr.it/doc?id=people______::fa577cc03550d472fe22c71ada549a45
Publikováno v:
Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society.
Publikováno v:
Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion.
Autor:
Marta Marchiori Manerba, Sara Tonelli
Publikováno v:
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)
Current abusive language detection systems have demonstrated unintended bias towards sensitive features such as nationality or gender. This is a crucial issue, which may harm minorities and underrepresented groups if such systems were integrated in r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::38f290cf001668a2eaf28df959b0bbf9
Publikováno v:
2021 IEEE Third International Conference on Cognitive Machine Intelligence (CogMI)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64e69da4eeab5a75e2d8dd9a4a3b1266